Paper: Exploring Syntactic Representations for Native Language Identification

ACL ID W13-1719
Title Exploring Syntactic Representations for Native Language Identification
Venue Innovative Use of NLP for Building Educational Applications
Session
Year 2013
Authors

Tree Substitution Grammar rules form a large and expressive class of features capable of rep- resenting syntactic and lexical patterns that provide evidence of an author?s native lan- guage. However, this class of features can be applied to any general constituent based model of grammar and previous work has done little to explore these options, relying primarily on the common Penn Treebank an- notation standard. In this work we contrast the performance of syntactic features for Na- tive Language Indentification using five dif- ferent formalisms. The use of different for- malisms captures complementary information from second language data, and can be used in combination to yield classification perfor- mance superior to any formalism taken on its own.